Method and device for extracting working face of tunnel worker and electronic equipment

Abstract

The invention provides a tunnel worker working face extraction method and device and electronic equipment, and belongs to the technical field of tunnel working faces. According to the method, the temporal geographic information data of tunnel workers can be collected, density clustering processing is carried out on the collected spatio-temporal data based on the DBScan algorithm, low-density position points low in work correlation are eliminated, and high-density position points high in work correlation are obtained. The position points with high density are further subjected to curve fitting, and the fitted curve section conforms to the linear structure characteristics of the tunnel and can serve as the working face of tunnel workers. The higher the density of the position points is, the higher the possibility of belonging to the actual work task is. According to the method, the working face of the tunnel worker is extracted based on the region with relatively high position point density in the temporal geographic information data of the tunnel worker, so that the error of a self-filling mode of the worker is avoided, and the accuracy of determining the working face is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of tunnel working faces, and in particular to a method, device and electronic equipment for extracting working faces of tunnel workers. Background Art

[0002] In the field of transportation, tunnel engineering mainly refers to buildings built underground or in mountains for motor vehicles to pass through. Tunnel construction is an important part of modern infrastructure construction. It is not only of great significance to the improvement of the transportation network, but also plays a key role in the development of the economy and society. Tunnel engineering project management is a complex and multifaceted task involving multiple links and elements. Tunnel engineering project management can be divided into work task management for different staff members. For example, task allocation and task progress management for tunnel staff. For another example, in a tunnel project, different staff members can be assigned work tasks in different spatial locations, and then the next task allocation can be carried out according to the completion progress of the assigned tasks.

[0003] In the traditional method, after receiving and completing the work tasks, the workers can report the completion of the work tasks by themselves, for example, a person completed a construction task in a certain section of the tunnel on a certain day. The workers performed the work tasks in a certain section of the tunnel, and this section of the tunnel can be regarded as the working surface of the workers. However, the working surface reported by the workers themselves may have errors, for example, the completion of the task of section A is mistakenly recorded as the completion of the task of section B. This leads to the low accuracy of the existing method of workers self-reporting the working surface. Summary of the invention

[0004] The present invention provides a method, device and electronic equipment for extracting the working face of tunnel workers, so as to solve the problem of low accuracy of the working face of tunnel workers determined by the prior art.

[0005] In a first aspect, the present invention provides a method for extracting a working face of tunnel workers, comprising: acquiring temporal geographic information data of tunnel workers, wherein the temporal geographic information data includes location data of the workers in the tunnel at each time point; clustering the temporal geographic information data according to a preset neighborhood radius and minimum sample point based on a DBScan clustering algorithm to obtain a working feature clustering result, wherein the neighborhood radius and the minimum sample point are determined based on the location point density of the workers at work; based on the least squares method, performing curve fitting on each location data in the working feature clustering result to obtain a fitted curve segment, wherein the endpoints of the curve segment are determined based on the extreme points in the working feature clustering result; and using the fitted curve segment as the working face of the tunnel workers.

[0006] In a possible implementation, after acquiring the temporal geographic information data of the tunnel workers, it also includes: performing median filtering on the temporal geographic information data to obtain processed temporal geographic information data; correspondingly, clustering the temporal geographic information data includes: clustering the processed temporal geographic information data.

[0007] In a possible implementation, median filtering the temporal geographic information data includes: taking any position point in the temporal geographic information data as a first target position point; taking the time of the first target position point as a starting point, extracting m position points in chronological order, where m is an odd number; respectively calculating the distances of the m position points relative to the origin; sorting the m position points according to the distances of the m position points relative to the origin to obtain a sorted sequence; and using the position point data of the center point of the sorted sequence as a filter output value to replace the first target position point data.

[0008] In one possible implementation, the filtering output value is determined based on the following formula:

[0009] y i =Med{f i-v ,…f i ,…f i+v}i∈N

[0010] Among them, y i Indicates the filter output value; f i represents the i-th position in the sorted sequence; f i-v Indicates the ivth position in the sorted sequence; f i+v Indicates the i+vth position point in the sorted sequence;

[0011] In a possible implementation, median filtering is performed on the temporal geographic information data to obtain processed temporal geographic information data, including: median filtering is performed on the temporal geographic information data to obtain denoised data; connecting each position point in the denoised data in chronological order to obtain a trajectory curve; and data compression is performed on the trajectory curve based on a point-by-point backward method of dynamic programming to obtain processed temporal geographic information data.

[0012] In a possible implementation, the DBScan clustering algorithm is based on which the temporal geographic information data is clustered according to a preset neighborhood radius and minimum sample point to obtain a working feature clustering result, including: taking any location point in the temporal geographic information data as a second target location point; obtaining the distance between the second target location point and other location points; taking the second target location point as the center of a circle, when the number of location points within the neighborhood radius is not less than the minimum sample point, confirming the second target location point as a core point; determining all points within the core point as the same cluster, and recursively expanding the cluster to obtain a working feature clustering result.

[0013] In a second aspect, the present invention provides a device for extracting a working face of tunnel workers, comprising: an acquisition module for acquiring temporal geographic information data of tunnel workers, wherein the temporal geographic information data includes location data of workers in the tunnel at each time point; a clustering module for clustering the temporal geographic information data based on a DBScan clustering algorithm according to a preset neighborhood radius and minimum sample point to obtain a working feature clustering result, wherein the neighborhood radius and the minimum sample point are determined based on the location point density of the workers at work; a fitting module for performing curve fitting on each location data in the working feature clustering result based on the least squares method to obtain a fitted curve segment, wherein the endpoints of the curve segment are determined based on the extreme points in the working feature clustering result; a working face determination module for using the fitted curve segment as the working face of the tunnel worker.

[0014] In a possible implementation, after acquiring the temporal geographic information data of the tunnel workers, it also includes: performing median filtering on the temporal geographic information data to obtain processed temporal geographic information data; correspondingly, clustering the temporal geographic information data includes: clustering the processed temporal geographic information data.

[0015] In a third aspect, the present invention provides an electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the processor implements the steps of the method described in the first aspect or any possible implementation manner of the first aspect.

[0016] In a fourth aspect, the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method described in the first aspect or any possible implementation of the first aspect are implemented.

[0017] The present invention provides a method, device and electronic device for extracting the working surface of tunnel workers. The present invention collects the temporal geographic information data of tunnel workers, performs density clustering processing on the collected spatiotemporal data based on the DBScan algorithm, excludes low-density location points with low work relevance, and obtains high-density location points with high work relevance. The location points with higher density are further subjected to curve fitting, and the curve segments after fitting conform to the linear structural characteristics of the tunnel, and can be used as the working surface of the tunnel workers. The greater the density of the location points, the greater the possibility that they belong to the actual work task. The present invention extracts the working surface of the tunnel workers based on the area with higher density of location points in the temporal geographic information data of the tunnel workers, avoids the error of the self-reporting method of the workers, and improves the accuracy of determining the working surface. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0019] Figure 1 This is an application scenario diagram of the tunnel worker working face extraction method provided by an embodiment of the present invention;

[0020] Figure 2 It is a flow chart of the implementation of the method for extracting the working face of tunnel workers provided by an embodiment of the present invention;

[0021] Figure 3 is a schematic diagram of a point-by-point retreat method based on dynamic programming provided by an embodiment of the present invention;

[0022] Figure 4 is a schematic diagram of original data distribution provided by an embodiment of the present invention;

[0023] Figure 5 is a schematic diagram of compressed data distribution provided by an embodiment of the present invention;

[0024] Figure 6 is a schematic diagram of clustering result distribution provided by an embodiment of the present invention;

[0025] Figure 7 is a schematic diagram of a fitted curve provided by an embodiment of the present invention;

[0026] Figure 8 is a schematic diagram of a working surface boundary curve provided by an embodiment of the present invention;

[0027] Fig. 9 is a schematic diagram of the working surface of a worker 794 on different days provided by an embodiment of the present invention;

[0028] Fig.10 is a schematic diagram of the working surface of a worker 639 on different days provided by an embodiment of the present invention;

[0029] Fig.11 is a schematic diagram of the working surface of the worker 934 on different days provided by an embodiment of the present invention;

[0030] Fig.12 755 is a schematic diagram of the working surface of workers on different days provided by an embodiment of the present invention;

[0031] Fig.13 It is a schematic diagram of the working surface of two workers on the 3rd provided by an embodiment of the present invention;

[0032] Fig.14 It is a schematic diagram of the working surface of two workers on the 10th provided by an embodiment of the present invention;

[0033] Fig.15 It is a schematic diagram of the working surface of two workers on the 15th provided by an embodiment of the present invention;

[0034] Fig.16 It is a schematic diagram of the working surface of two workers on the 20th provided by an embodiment of the present invention;

[0035] Fig.17 It is a schematic structural diagram of a tunnel worker working face extraction device provided by an embodiment of the present invention;

[0036] Fig.18 is a schematic diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0037] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present invention. However, it should be clear to those skilled in the art that the present invention may be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present invention.

[0038] In order to make the purpose, technical solutions and advantages of the present invention more clear, specific embodiments will be described below in conjunction with the accompanying drawings.

[0039] Figure 1 This is an application scenario diagram of the tunnel worker working face extraction method provided by an embodiment of the present invention. Figure 1As shown in the figure, in tunnel projects, there are usually multiple workers, and tunnel construction tasks can also be divided into multiple types. The same type of construction tasks can also be divided into multiple sections for execution. Setting up multiple working faces at the same time can improve the efficiency of tunnel construction. Therefore, in tunnel projects, different workers can be assigned work tasks in different spatial locations. The work tasks in the same spatial location may also be assigned to multiple workers. The work tasks of different workers may also overlap in space. Further considering the time dimension, the project tasks performed by each worker every day and the section of the tunnel where the work tasks are performed may also be different. At the end of each day, the next task allocation needs to be made based on the completion progress of the assigned tasks that day. It can be seen that the accurate determination of the working faces of workers in tunnel construction is particularly important for tunnel construction management.

[0040] The embodiment of the present invention solves the problem of low accuracy of the working face of tunnel workers determined by the prior art by extracting the working face of tunnel workers based on the area with higher density of location points in the temporal geographic information data of tunnel workers.

[0041] Figure 2 is a flowchart of the method for extracting the working face of tunnel workers provided by an embodiment of the present invention, referring to Figure 2 , as detailed below:

[0042] In step 201, the temporal geographic information data of the tunnel workers is obtained, wherein the temporal geographic information data includes the location data of the workers in the tunnel at each time point.

[0043] It should be noted that before step 201, the tunnel staff receives a work task, for example, a work task may be: someone goes to a certain section of the tunnel on a certain day to complete a certain type of construction task. When performing the work task, the tunnel staff will move frequently inside the tunnel. Thus, spatiotemporal data is continuously generated in the process of performing the work task, such as a certain location at a certain time.

[0044] In some embodiments, the location data of the workers in the tunnel at each time point can be collected by sensors to obtain the temporal geographic information data of the tunnel workers. The form of the sensor is not limited here. For example, a radio frequency identification sensor can be used.

[0045] It should be noted that temporal geographic information data is also called TGIS (Spatial-Temporal GIS). TGIS has become a hot topic in GIS research, and it can provide information about the changes of geographic objects in time and space.

[0046] The temporal geographic information data obtained in step 201 is used to extract the working faces of tunnel workers in subsequent steps 203-204. The embodiment of the present invention can extract the working faces of different workers by processing TGIS data. These data can provide a scientific basis to help researchers and decision makers gain a deeper understanding of the laws and trends of spatiotemporal phenomena.

[0047] The following table is an example of the temporal geographic information data of tunnel workers provided by an embodiment of the present invention. Referring to the following table, the temporal geographic information data of a tunnel worker on a certain day is selected. In the data collected by the sensor, there is the spatial position of the personnel at a certain point in time. The data collected by the sensor on a certain day is windowed and some data is extracted. Time represents time, 604 and 755 represent the IDs of two different workers respectively, and the position data is represented in the format of (x, y).

[0048] Time 604 755 04 / 10-00:00:00 (153.86,111.12) (-46.27,-54.56) 04 / 10-00:00:02 (153.91,111.05) (-46.27,-54.55) …… …… …… 04 / 10-01:00:00 (152.57,112.64) (-46.27,-54.56) 04 / 10-01:00:02 (152.58,112.63) (-46.39,-54.38) 04 / 10-01:00:04 (152.55,112.66) (-46.29,-54.57) …… …… …… 04 / 10-23:00:08 (152.51,112.65) (-46.34,-54.37) 04 / 10-23:00:10 (152.56,112.66) (-46.39,-54.51)

[0049] From the table above, we can see that the sensor collects data at an interval of about 2 seconds, and the amount of data in one day reaches more than 40,000. By observing the location information, we can find that the range of activities of each staff member is limited every day and there will not be a big change. Since the sensor will also produce some deviations and redundancy when collecting data, some data processing can be performed after extracting the data.

[0050] On the one hand, how to process large-scale spatiotemporal data and improve the efficiency and performance of data processing is a difficult problem; on the other hand, how to choose a suitable method for processing to ensure the accuracy and credibility of the data is also a difficult problem. In the face of these challenges, the embodiment of the present invention proposes a method using data mining technology, taking a tunnel worker as the research object, extracting key features from the original trajectory, and finally accurately extracting the working face, providing a basis for project decision makers to make judgments. The development of data mining technology has obvious advantages in cleaning abnormal data of massive data and data processing accuracy.

[0051] In a possible implementation, after acquiring the temporal geographic information data of the tunnel workers, it also includes: performing median filtering on the temporal geographic information data to obtain processed temporal geographic information data; correspondingly, clustering the temporal geographic information data includes: clustering the processed temporal geographic information data.

[0052] The embodiment of the present invention performs median filtering on the acquired temporal geographic information data and uses the median filtering technology to process the initial vector data, which can not only effectively suppress isolated noise points, but also better maintain the original shape and characteristics of the data without causing significant deformation of the vector. At the same time, the denoised data improves the efficiency and accuracy of the subsequent extraction steps.

[0053] Median filtering is a nonlinear digital signal processing technology. It replaces the value of each point in the digital sequence with the median of the value of the point and its neighborhood. To use median filtering for data processing, you need to take a window m (m is an odd number) in advance, then take m numbers from the input sequence one after another, sort these m numbers by size, and take the number with the center point as the filter output.

[0054] In one possible implementation, median filtering of temporal geographic information data includes: taking any position point in the temporal geographic information data as the first target position point; taking the time of the first target position point as the starting point, extracting m position points in chronological order, where m is an odd number; respectively calculating the distances of the m position points relative to the origin; sorting the m position points according to the distances of the m position points relative to the origin to obtain a sorted sequence; and using the position point data of the center point of the sorted sequence as the filter output value to replace the first target position point data.

[0055] In one possible implementation, the filtering output value is determined based on the following formula:

[0056] y i =Med{f i-v ,…f i ,…f i+v}i∈N

[0057] Among them, y i Indicates the filter output value; f i represents the i-th position in the sorted sequence; f i-v Indicates the ivth position in the sorted sequence; f i+v Indicates the i+vth position point in the sorted sequence;

[0058] The above embodiments perform median filtering on the acquired raw temporal geographic information data. The amount of raw data is huge. Even after the median filtering technology is applied, the amount of data still appears to be huge and redundant. Due to the frequent acquisition time, most points are not critical paths. Therefore, the following embodiments select a point-by-point backward compression algorithm based on dynamic programming to compress the data and extract key feature points for further observation and processing.

[0059] In a possible implementation, median filtering is performed on the temporal geographic information data to obtain processed temporal geographic information data, including: median filtering is performed on the temporal geographic information data to obtain denoised data; connecting each position point in the denoised data in chronological order to obtain a trajectory curve; and data compression is performed on the trajectory curve based on a point-by-point backward method of dynamic programming to obtain processed temporal geographic information data.

[0060] Figure 3 is a schematic diagram of a point-by-point backtracking method based on dynamic programming provided by an embodiment of the present invention; Figure 3 , the optimization process of the data in this paper is to use the DP (dynamic programming) algorithm. First, the original vector points are piecewise linearly fitted according to the feature points after the curve compression. Then, the error of the fitted linear fitting curve and the compressed feature curve is compared through the Euclidean distance between the vector point and the feature curve between the two feature points. The curve with the smaller error is selected as the final curve after optimization until all curves are compared. Then, all curves are connected to obtain the final optimization curve, and the global optimum is achieved through the local optimum. Because the dynamic programming algorithm does not set the threshold when compressing, it may cause the error of the compressed point distance to the compressed curve to be too large, affecting the overall compression error. Therefore, the threshold limit is added when the dynamic programming algorithm is used for compression. The employee's forward direction and work scope can be predicted based on the optimization curve, and experimental analysis can be made based on the proposed DP algorithm scheme.

[0061] The formula for dynamic programming compression is as follows:

[0062] DP[n]=DP[n-1]+min{e(n),E(n)}

[0063] In the formula, DP[n] is the error of the first n curves, e(n) is the error from the vector point in the nth curve to the compression curve obtained by the dynamic programming algorithm, and E(n) is the error from the vector point in the nth curve to the compression curve obtained by the point-by-point backward method. Compare the two and take the minimum value. The final DP[n] is the minimum compression error.

[0064] Therefore, the steps of the dynamic programming algorithm used in the embodiment of the present invention are as follows.

[0065] (1) Compress the route using the point-by-point back-stepping method and DP algorithm to obtain a compressed curve;

[0066] (2) Using a dynamic programming algorithm to compress the characteristic points of the compression curve in a back-to-forward manner;

[0067] (3) After the dynamic compression algorithm is implemented, when the compression error is less than the error obtained by curve compression, and the thresholds of all vector points to the curve are within the thresholds set by the curve compression algorithm, the compressed curve obtained by dynamic programming is replaced; otherwise, the compressed curve obtained by the point-by-point backward method is saved.

[0068] In a possible implementation, the trajectory curve is compressed based on a point-by-point backward method of dynamic programming, and the processed temporal geographic information data includes:

[0069] Determining an end point in the trajectory curve;

[0070] Taking the end point as the compression starting point, taking the previous data point of the compression starting point as the target point, taking the previous data point of the target point as the compression end point, and obtaining a target line segment formed by the compression starting point and the compression end point;

[0071] Starting from the end point, searching for the initial feature point in the trajectory curve point by point from back to front according to the distance from the target point to the target line segment;

[0072] Performing piecewise curve compression on the data points in the trajectory curve based on the initial feature points based on dynamic programming, and obtaining a first compression error corresponding to two optimized feature points of the piecewise curve compression;

[0073] Each of the first compression errors is compared with the second compression error corresponding to the corresponding initial feature point in turn, and a final curve compression result of the trajectory curve is obtained according to the comparison result.

[0074] The embodiment of the present invention determines the end point in the trajectory curve, then uses the end point as the compression start point, uses the previous data point of the compression start point as the target point, and uses the previous data point of the target point as the compression end point to obtain a target line segment formed by the compression start point and the compression end point, and then starts from the end point and searches for the initial feature point in the trajectory curve point by point from far to near according to the distance from the target point to the target line segment, so that starting from the end point, only one feature point search from back to front can be performed, thereby reducing repeated cycle judgments, greatly reducing the time required for compression, and improving compression efficiency. On this basis, according to the initial feature points, the data points in the trajectory curve are compressed in piecewise curves based on dynamic programming, and the first compression errors corresponding to the two optimized feature points of the piecewise curve compression are obtained, and each first compression error is compared with the second compression error corresponding to the corresponding initial feature point in turn, and the final curve compression result of the trajectory curve is obtained according to the comparison result. On the one hand, the search range of dynamic programming can be narrowed according to the initial feature points, and the limitations of dynamic programming on processor space occupancy and computing speed can be reduced. On the other hand, according to the first compression error corresponding to the optimized feature points of piecewise curve compression based on dynamic programming and the second compression error corresponding to the corresponding initial feature points, the feature points with smaller compression errors are selected to obtain the final curve compression result, which can further reduce the error of curve compression and obtain better curve compression results.

[0075] In a possible implementation, starting from the end point, searching for the initial feature point in the trajectory curve point by point from back to front according to the distance from the target point to the target line segment includes:

[0076] Recording the end point as an initial feature point, and calculating the distance from the target point to the target line segment;

[0077] If the distance is less than the set threshold, the compression end point is taken as a new target point, the previous data point of the compression end point is taken as a new compression end point, and the step of "obtaining a target line segment formed by the compression start point and the compression end point" and its subsequent steps are re-executed;

[0078] If the distance is greater than or equal to the set threshold, the target point is recorded as an initial feature point, and the target point is used as a new compression starting point, and the step of "using the previous data point of the compression starting point as the target point and the previous data point of the target point as the compression end point to obtain the target line segment formed by the compression starting point and the compression end point" and its subsequent steps are re-executed;

[0079] When the new compression end point is the starting point in the trajectory curve, the starting point is recorded as an initial feature point, and all the initial feature points are obtained.

[0080] Figure 4 is a schematic diagram of original data distribution provided by an embodiment of the present invention; Figure 5 : is a schematic diagram of compressed data distribution provided by an embodiment of the present invention; the horizontal axis represents the x-coordinate and the vertical axis represents the y-coordinate. Figure 4 , Figure 5 These are the distribution diagrams of the original trajectory and compressed trajectory of the staff member with ID 755 on October 3.

[0081] In step 202, based on the DBScan clustering algorithm, the temporal geographic information data is clustered according to a preset neighborhood radius and minimum sample point to obtain a work feature clustering result, wherein the neighborhood radius and the minimum sample point are determined based on the location point density of the staff at work.

[0082] The present invention aims to find the most frequent trajectory segments of the workers in a day, that is, to find the work surface and then analyze it. Therefore, the characteristic trajectory can be clustered. It can be seen from the original trajectory characteristics that the density of the most frequent trajectory segment is the largest. The greater the density of the position points, the greater the correlation with the work; the smaller the density of the position points, the smaller the correlation with the work. Therefore, DBScan, a density-based clustering algorithm, can be selected.

[0083] In a possible implementation, based on the DBScan clustering algorithm, the temporal geographic information data is clustered according to a preset neighborhood radius and minimum sample point, and the working feature clustering result is obtained, including: taking any position point in the temporal geographic information data as a second target position point; obtaining the distance between the second target position point and other position points; taking the second target position point as the center of the circle, when the number of position points within the neighborhood radius is not less than the minimum sample point, confirming the second target position point as a core point; determining all points within the core point as the same cluster, and recursively expanding the cluster to obtain the working feature clustering result.

[0084] For example, the cluster is initialized based on the given neighborhood radius and minimum sample point. Then, for each data point, its distance to other data points is calculated. If the number of data points within the distance range is not less than the minimum sample point, the data point is a core point. For a core point, the points in its neighborhood are marked as the same cluster, and the cluster is recursively expanded; for points that are not core points but in the neighborhood of the core point, they are marked as boundary points.

[0085] For example, the neighborhood radius can be selected as 0.3 according to the characteristics of the tunnel staff data. Further, according to the fact that the kth nearest neighbors in a class are roughly the same distance, a k-distance graph is drawn and it is found that 5 is the inflection point of the image, so the minimum sample point is selected as 5. Figure 6 Schematic diagram of clustering result distribution provided by an embodiment of the present invention. The horizontal axis represents the x-coordinate, and the vertical axis represents the y-coordinate. Different colors represent different clusters. Figure 6 , exemplary, Figure 6 This is a schematic diagram of the clustering results of the characteristic trajectory of the staff member with ID 755 under this parameter.

[0086] In step 203, based on the least squares method, curve fitting is performed on each position data in the working feature clustering result to obtain a fitted curve segment, wherein the endpoints of the curve segment are determined based on the extreme points in the working feature clustering result.

[0087] The working surface is in the most frequent trajectory segment, and a suitable curve needs to be fitted to replace the original point. The embodiment of the present invention selects the least squares method for curve fitting. The goal of the least squares algorithm is to find a straight line or curve that minimizes the sum of the squares of the vertical distances from the observed data points to the straight line or curve.

[0088] For a set of data points (x1, y1), (x2, y2), ..., (xn, yn), the function model to be fitted is y = f(x, θ), where θ is the parameter of the model. The goal of the least squares method is to find the optimal parameter θ so that the residual sum of squares is minimized, that is: Reach the minimum value. The specific implementation steps and formula are as follows:

[0089] Step ①, collect data on independent variables x and dependent variables y.

[0090] Step ②, assume that the linear regression model is y=β0+β1.

[0091] Step ③, determine the parameters by minimizing the residual sum of squares, the formula is

[0092] Step ④, calculate the partial derivatives of the residual sum of squares with respect to parameters β0 and β1 respectively, and set the partial derivatives to zero, and obtain the equation system Solve for the parameters β0 and β1.

[0093] Step ⑤, substitute the obtained parameters into the model to obtain the fitted linear regression model.

[0094] Step ⑥, use the fitted model to predict the new independent variable and obtain the predicted value of the dependent variable.

[0095] Figure 7 is a schematic diagram of a fitted curve provided in an embodiment of the present invention; Figure 7 , the red line is the fitting curve.

[0096] In step 204, the fitted curve segment is used as the working surface for the tunnel workers.

[0097] The embodiment of the present invention collects the temporal geographic information data of the tunnel workers, performs density clustering processing on the collected spatiotemporal data based on the DBScan algorithm, eliminates low-density location points with low relevance to the work, and obtains high-density location points with high relevance to the work. The location points with higher density are further subjected to curve fitting, and the curve segments after fitting conform to the linear structural characteristics of the tunnel, and can be used as the working surface of the tunnel workers. The greater the density of the location points, the greater the possibility that they belong to the actual work tasks. The present invention extracts the working surface of the tunnel workers based on the areas with higher density of location points in the temporal geographic information data of the tunnel workers, avoids errors in the self-reporting method of the workers, and improves the accuracy of determining the working surface.

[0098] Figure 8 is a schematic diagram of a working surface boundary curve provided by an embodiment of the present invention; Figure 8The working surface is used to represent the specific work content and scope faced by a worker at work, such as a plane that can represent the activity trajectory of tunnel workers. The requirement for the working surface is to include 95% of the original points, so the concept of percentile in statistics is introduced here. To filter out the working surface, you can choose the 5th percentile, which represents the value at the 5th percentile position after a set of data is sorted from small to large. 5% of the data values ​​are less than or equal to this number, and the remaining 95% of the data values ​​are greater than this number. Use it as an offset, so that a boundary line can be drawn above the fitting curve to represent the approximate range or boundary of the data. At this time, the boundary line is the final working surface.

[0099] The embodiment of the present invention continues to use the tunnel staff working face extraction method to process the trajectories of different personnel on different days to obtain more working face data. The following is part of the extracted data, which is named as id number_day number, representing the working face of a certain numbered personnel on the numbered day.

[0100] Fig. 9 is a schematic diagram of the working surface of a worker 794 on different days provided by an embodiment of the present invention; Fig.10 is a schematic diagram of the working surface of a worker 639 on different days provided by an embodiment of the present invention; Fig.11 is a schematic diagram of the working surface of the worker 934 on different days provided by an embodiment of the present invention; Fig.12 Schematic diagram of the working surface of the staff 755 on different days provided by the embodiment of the present invention; Figure 9-12 , some potential information can be mined, such as determining that the hot spot activity area of ​​794 staff is near the horizontal axis -110 to -115, and inferring that 755 staff concentrated on completing work in a certain area for a period of time. This potential information will help managers further schedule and allocate resources and better monitor the progress of project implementation.

[0101] Fig.13 It is a schematic diagram of the working surface of two workers on the 3rd provided by an embodiment of the present invention; Fig.14 It is a schematic diagram of the working surface of two workers on the 10th provided by an embodiment of the present invention; Fig.15 It is a schematic diagram of the working surface of two workers on the 15th provided by an embodiment of the present invention; Fig.16 This is a schematic diagram of the working face of two workers on the 20th provided by an embodiment of the present invention; similar working face analysis, if an exploration worker has a similar trajectory with another worker on the same day, it can be concluded that they are working in the same working group on that day. Figure 13-Figure 16, which is the similar trajectory of different staff members on the same day. From the results, we can see that some staff members have some intersections in their work. These data can show that their work progress is relatively consistent, and the various work faces cooperate well with each other, which is conducive to the advancement of the overall project. At the same time, it also gives decision makers some information tips, such as the relatively balanced distribution of resources (such as materials, equipment, etc.), and each work face can get the support it needs.

[0102] The embodiment of the present invention takes the work trajectory data of tunnel workers as the research object, focuses on the extraction and analysis of the work surface, uses filtering technology and compression technology to remove the noise and redundancy of a large amount of trajectory data, clusters the key data, accurately identifies the clustering structure in the data, and finally uses the least squares method to fit the shape characteristics of the tunnel workers' work surface, and finds the high similarity of some workers' trajectories. This is a powerful supplement to the existing TGIS data research system, and provides a scientific basis for decision makers to analyze and schedule project progress.

[0103] Due to the singleness of the data, the potential information of the mined data is not sufficient. If it is combined with other relevant data, such as environmental monitoring data, resource scheduling data, worker status data, etc., a more comprehensive analysis can be performed. At the same time, it is also possible to further predict the behavior of tunnel workers based on the fitted working face information based on relevant machine learning and other technologies. The research on the working face needs to expand its scope and depth to provide more favorable support for the development of tunnel engineering.

[0104] It should be understood that the order of execution of the steps in the above embodiment does not necessarily mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present invention.

[0105] The following is an embodiment of the device of the present invention. For details not described in detail therein, reference may be made to the corresponding method embodiment described above.

[0106] Fig.17 : is a schematic diagram of the structure of the tunnel worker working face extraction device provided by an embodiment of the present invention. For the convenience of explanation, only the parts related to the embodiment of the present invention are shown, which are described in detail as follows:

[0107] Reference Fig.17 , the tunnel staff working face extraction device 3 includes:

[0108] The acquisition module 31 is used to acquire the temporal geographic information data of the tunnel workers, wherein the temporal geographic information data includes the location data of the workers in the tunnel at each time point.

[0109] The clustering module 32 is used to cluster the temporal geographic information data based on the DBScan clustering algorithm according to the preset neighborhood radius and minimum sample point to obtain the work feature clustering result, wherein the neighborhood radius and the minimum sample point are determined based on the location point density of the staff at work.

[0110] The fitting module 33 is used to perform curve fitting on each position data in the working feature clustering result based on the least square method to obtain a fitted curve segment, wherein the endpoints of the curve segment are determined based on the extreme value points in the working feature clustering result.

[0111] The working face determination module 34 is used to use the fitted curve segment as the working face of the tunnel workers.

[0112] The embodiment of the present invention collects the temporal geographic information data of the tunnel workers, performs density clustering processing on the collected spatiotemporal data based on the DBScan algorithm, eliminates low-density location points with low relevance to the work, and obtains high-density location points with high relevance to the work. The location points with higher density are further subjected to curve fitting, and the curve segments after fitting conform to the linear structural characteristics of the tunnel, and can be used as the working surface of the tunnel workers. The greater the density of the location points, the greater the possibility that they belong to the actual work tasks. The present invention extracts the working surface of the tunnel workers based on the areas with higher density of location points in the temporal geographic information data of the tunnel workers, avoids errors in the self-reporting method of the workers, and improves the accuracy of determining the working surface.

[0113] In a possible implementation, after acquiring the temporal geographic information data of the tunnel workers, it also includes: performing median filtering on the temporal geographic information data to obtain processed temporal geographic information data; correspondingly, clustering the temporal geographic information data includes: clustering the processed temporal geographic information data.

[0114] Fig.18 Schematic diagram of an electronic device provided by an embodiment of the present invention. Fig.18 As shown, the electronic device 4 of this embodiment includes: a processor 40, a memory 41, and a computer program 42 stored in the memory 41 and executable on the processor 40. When the processor 40 executes the computer program 42, the steps in the above-mentioned various tunnel worker working face extraction method embodiments are implemented, such as Figure 2 Alternatively, when the processor 40 executes the computer program 42, the functions of each module / unit in the above-mentioned device embodiments are realized, for example, Fig.17 The functions of the modules 31 to 34 are shown.

[0115] Exemplarily, the computer program 42 may be divided into one or more modules / units, which are stored in the memory 41 and executed by the processor 40 to implement the present invention. The one or more modules / units may be a series of computer program instruction segments capable of implementing specific functions, which are used to describe the execution process of the computer program 42 in the electronic device 4. For example, the computer program 42 may be divided into Fig.17 Modules 31 to 34 are shown.

[0116] The electronic device 4 may be a computing device such as a desktop computer, a notebook, a PDA, or a cloud server. The electronic device 4 may include, but is not limited to, a processor 40 and a memory 41. Those skilled in the art will appreciate that Fig.18 It is only an example of the electronic device 4 and does not constitute a limitation of the electronic device 4. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, the electronic device may also include input and output devices, network access devices, buses, etc.

[0117] The processor 40 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0118] The memory 41 may be an internal storage unit of the electronic device 4, such as a hard disk or memory of the electronic device 4. The memory 41 may also be an external storage device of the electronic device 4, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the electronic device 4. Further, the memory 41 may also include both an internal storage unit and an external storage device of the electronic device 4. The memory 41 is used to store the computer program and other programs and data required by the electronic device. The memory 41 may also be used to temporarily store data that has been output or is to be output.

[0119] The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0120] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0121] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0122] In the embodiments provided by the present invention, it should be understood that the disclosed devices / electronic devices and methods can be implemented in other ways. For example, the device / electronic device embodiments described above are only schematic. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0123] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0124] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0125] If the integrated module / unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, the steps of the above-mentioned tunnel staff working face extraction method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device that can carry the computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium.

[0126] The embodiments described above are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included in the protection scope of the present invention.

Claims

1. A method for extracting the working face of a tunnel worker, characterized in that: include: Acquire temporal geographic information data of tunnel workers, wherein the temporal geographic information data includes location data of the workers in the tunnel at each time point; Based on the DBScan clustering algorithm, the temporal geographic information data is clustered according to a preset neighborhood radius and minimum sample point to obtain a work feature clustering result, wherein the neighborhood radius and the minimum sample point are determined based on the location point density of the staff at work; Based on the least squares method, curve fitting is performed on each position data in the working feature clustering result to obtain a fitted curve segment, wherein the endpoints of the curve segment are determined based on the extreme value points in the working feature clustering result; The fitted curve segment is used as the working surface for tunnel workers.

2. The method for extracting the working face of tunnel workers according to claim 1, characterized in that: After obtaining the temporal geographic information data of the tunnel workers, it also includes: Performing median filtering on the temporal geographic information data to obtain processed temporal geographic information data; Correspondingly, clustering the temporal geographic information data includes: clustering the processed temporal geographic information data.

3. The method for extracting the working face of tunnel workers according to claim 2, characterized in that: Performing median filtering on the temporal geographic information data includes: Taking any location point in the temporal geographic information data as a first target location point; Taking the time of the first target position point as the starting point, extract m position points in chronological order, where m is an odd number; Calculate the distances of the m position points relative to the origin respectively; Sorting the m position points according to the distances of the m position points relative to the origin to obtain a sorted sequence; The position point data of the center point of the sorting sequence is used as the filter output value to replace the first target position point data.

4. The method for extracting the working face of tunnel workers according to claim 3, characterized in that: The filter output value is determined based on the following formula: y i =Med{f i-v ,…f i ,…f i+v }i∈N Among them, y i Indicates the filter output value; f i represents the i-th position in the sorted sequence; f i-v Indicates the ivth position in the sorted sequence; f i+v Indicates the i+vth position point in the sorted sequence; 5. The method for extracting the working face of tunnel workers according to claim 2, characterized in that: The temporal geographic information data is subjected to median filtering to obtain processed temporal geographic information data including: Performing median filtering on the temporal geographic information data to obtain denoised data; Connect each position point in the denoised data in chronological order to obtain a trajectory curve; The trajectory curve is compressed based on a point-by-point backward method of dynamic programming to obtain processed temporal geographic information data.

6. The method for extracting the working face of tunnel workers according to claim 1, characterized in that: Based on the DBScan clustering algorithm, the temporal geographic information data is clustered according to a preset neighborhood radius and minimum sample point, and the working feature clustering results obtained include: Using any location point in the temporal geographic information data as a second target location point; Obtaining the distance between the second target position point and other position points; Taking the second target position point as the center of the circle, when the number of position points within the neighborhood radius is not less than the minimum sample point, confirming the second target position point as a core point; All points within the core point are determined as the same cluster, and the cluster is recursively expanded to obtain a working feature clustering result.

7. A tunnel worker working face extraction device, characterized in that: include: An acquisition module, used to acquire temporal geographic information data of tunnel workers, wherein the temporal geographic information data includes location data of the workers in the tunnel at each time point; A clustering module, for clustering the temporal geographic information data based on a DBScan clustering algorithm according to a preset neighborhood radius and minimum sample point to obtain a work feature clustering result, wherein the neighborhood radius and the minimum sample point are determined based on the location point density of the staff at work; A fitting module, used for performing curve fitting on each position data in the working feature clustering result based on the least square method to obtain a fitted curve segment, wherein the endpoints of the curve segment are determined based on the extreme value points in the working feature clustering result; The working face determination module is used to use the fitted curve segment as the working face of the tunnel workers.

8. The tunnel worker working face extraction device according to claim 7, characterized in that: After obtaining the temporal geographic information data of the tunnel workers, it also includes: Performing median filtering on the temporal geographic information data to obtain processed temporal geographic information data; Correspondingly, clustering the temporal geographic information data includes: clustering the processed temporal geographic information data.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the tunnel worker working face extraction method as described in any one of claims 1 to 6 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method for extracting the working face of tunnel workers as described in any one of claims 1 to 6 above are implemented.

Images